| | --- |
| | library_name: peft |
| | license: bigscience-openrail-m |
| | tags: |
| | - paper |
| | - paper extract |
| | --- |
| | ## Training procedure |
| |
|
| | ### Framework versions |
| |
|
| |
|
| | - PEFT 0.4.0 |
| |
|
| | in https://github.com/hiyouga/ChatGLM-Efficient-Tuning/tree/main |
| |
|
| | CUDA_VISIBLE_DEVICES=3 nohup python src/web_demo.py \ |
| | --model_name_or_path /HOME/jack/model/chatglm-6b \ |
| | --checkpoint_dir paper_meta\ \ |
| | > log_web_demo.txt 2>&1 & tail -f log_web_demo.txt |
| | |
| |
|
| |
|
| | ### 🚩Citation |
| |
|
| | Please cite the following paper if you use jackkuo/PaperExtractGPT in your work. |
| |
|
| | ```bibtex |
| | @INPROCEEDINGS{10412837, |
| | author={Guo, Menghao and Wu, Fan and Jiang, Jinling and Yan, Xiaoran and Chen, Guangyong and Li, Wenhui and Zhao, Yunhong and Sun, Zeyi}, |
| | booktitle={2023 IEEE International Conference on Knowledge Graph (ICKG)}, |
| | title={Investigations on Scientific Literature Meta Information Extraction Using Large Language Models}, |
| | year={2023}, |
| | volume={}, |
| | number={}, |
| | pages={249-254}, |
| | keywords={Measurement;Knowledge graphs;Information retrieval;Data mining;Task analysis;information extraction;large language model;scientific literature}, |
| | doi={10.1109/ICKG59574.2023.00036}} |
| | ``` |
